A digital technique for art authentication

Abstract

We describe a computational technique for authenticating works of art, specifically paintings and drawings, from high-resolution digital scans of the original works. This approach builds a statistical model of an artist from the scans of a set of authenticated works against which new works then are compared. The statistical model consists of first-and higher-order wavelet statistics. We show preliminary results from our analysis of 13 drawings that at various times have been attributed to Pieter Bruegel the Elder; these results confirm expert authentications. We also apply these techniques to the problem of determining the number of artists that may have contributed to a painting attributed to Pietro Perugino and again achieve an analysis agreeing with expert opinion. I t probably was not long after people began paying money for art that a lucrative business in forging art was born, and it probably was not too much later that techniques for detecting art forgeries emerged. Even today, the early techniques for authentication remain preeminent. By and large, these techniques are based on ''connoisseurship'' and so rely on the discerning eyes of a few experts who are steeped in the work and life of the artist in question. Their opinion may be informed by the ''catalogue raison,'' which is the current acknowledged authoritative work on the artist's oeuvre. Other desiderata may include provenance that might be traced back to the artist's circle or his collectors and makes possible the comparison of the work's implicit biography with the histories of related works or even a detailed analysis of any signature that may be present. (See ref. 1 for a survey of current techniques.)In addition to the reliance on the human actor, quantitative methods can be brought to bear. X-ray analysis can reveal a painting beneath a painting that can shed light on its origins. Surface analysis of the painting materials is another approach, most famously applied in the investigation of the famous ''van Meerghen forgeries.'' In this case, the forgery of paintings attributed to Johannes Vermeer was confirmed by dating the paintings according to the proportion of a certain lead isotope in the lead-based paint. An elementary application of differential equations allowed for the actual isotope content to be compared with the expected content had the work been painted in Vermeer's day (2). This technique marked a first use of mathematics in the service of art authentication.With the advent of powerful digital technology, computational tools may be able to provide new insights into and techniques for the art and science of art authentication. For example, a fractal analysis of Jackson Pollock's drip paintings has revealed interesting relations between the evolution of Pollock's aesthetic and the fractal dimension of his work (3, 4). The analysis also raises the possibility of using fractal dimension to help authenticate work attributed to Pollock. Various techniques from machine learning have been applied to the analysis and classification of ''...

Detection of forgery in paintings using supervised learning

“…For example, Lyu, Rockmore, and Farid found that real Brueghel drawings can be distinguished from imitations via a variety of statistics of the wavelet coefficients [3]. This approach was further extended to the faces of a Perugino painting thought to be painted by several hands; the three faces that clustered in this analysis agreed with the three that art experts think were painted by the same hand.…”

“…This assumes that an artist's brushwork is characterized by signature features (caused, e.g., by the artist's habitual physical movements) which might be found by machine learning methods and used as an additional piece of evidence to rule upon authenticity. Indeed, early attempts in this area have already found considerable success [2,3,4,5,6]. …”

Quantitative criticism of literary relationships

“…Finally, quantitative stylometric analyses have long been used to clarify gross relationships between texts. Standard applications of stylometry include dating literary works and resolving questions of attribution (26)(27)(28)(29)(30). Both ad hoc stylometric analysis and supervised machine learning with stylometric features have proven successful for such applications (31)(32)(33), including for cases in Latin literature (34).…”

Graph-based methods for the automatic annotation and retrieval of art prints

“…The main focus of the papers is on the artistic identification problem, where the goal is to classify original and fake paintings of a given artist [4,32,39] or to produce stylistic analysis of paintings [20,24,25]. Most of the methods above can be regarded as adaptations from the content-based image retrieval systems [14], where the emphasis is placed on the characterization of brush strokes using texture or color.…”